{"id":"https://openalex.org/W2886260596","doi":"https://doi.org/10.18653/v1/d18-1532","title":"LemmaTag: Jointly Tagging and Lemmatizing for Morphologically Rich Languages with BRNNs","display_name":"LemmaTag: Jointly Tagging and Lemmatizing for Morphologically Rich Languages with BRNNs","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2886260596","doi":"https://doi.org/10.18653/v1/d18-1532","mag":"2886260596"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d18-1532","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1532","pdf_url":"https://www.aclweb.org/anthology/D18-1532.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D18-1532.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025622090","display_name":"Daniel Kondratyuk","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I1344076864","display_name":"Center for Applied Linguistics","ror":"https://ror.org/020pekv35","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1344076864"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Kondratyuk","raw_affiliation_strings":["Institute of Formal and Applied Linguistics,","Google (United States), Mountain View, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Formal and Applied Linguistics,","institution_ids":["https://openalex.org/I1344076864"]},{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033114427","display_name":"Tom\u00e1\u0161 Gaven\u010diak","orcid":"https://orcid.org/0000-0003-1119-2426"},"institutions":[{"id":"https://openalex.org/I21250087","display_name":"Charles University","ror":"https://ror.org/024d6js02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21250087"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Tom\u00e1\u0161 Gaven\u010diak","raw_affiliation_strings":["Charles University, Prague, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Charles University, Prague, Czechia","institution_ids":["https://openalex.org/I21250087"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060081515","display_name":"Milan Straka","orcid":"https://orcid.org/0000-0003-3295-5576"},"institutions":[{"id":"https://openalex.org/I1344076864","display_name":"Center for Applied Linguistics","ror":"https://ror.org/020pekv35","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1344076864"]},{"id":"https://openalex.org/I21250087","display_name":"Charles University","ror":"https://ror.org/024d6js02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21250087"]}],"countries":["CZ","US"],"is_corresponding":false,"raw_author_name":"Milan Straka","raw_affiliation_strings":["Institute of Formal and Applied Linguistics,","Charles University, Prague, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Formal and Applied Linguistics,","institution_ids":["https://openalex.org/I1344076864"]},{"raw_affiliation_string":"Charles University, Prague, Czechia","institution_ids":["https://openalex.org/I21250087"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102738283","display_name":"Jan Haji\u010d","orcid":"https://orcid.org/0000-0002-3503-7730"},"institutions":[{"id":"https://openalex.org/I21250087","display_name":"Charles University","ror":"https://ror.org/024d6js02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21250087"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan Haji\u010d","raw_affiliation_strings":["Charles University, Prague, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Charles University, Prague, Czechia","institution_ids":["https://openalex.org/I21250087"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/lemmatisation","display_name":"Lemmatisation","score":0.8845146298408508},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8190890550613403},{"id":"https://openalex.org/keywords/czech","display_name":"Czech","score":0.7601318359375},{"id":"https://openalex.org/keywords/part-of-speech-tagging","display_name":"Part-of-speech tagging","score":0.699059009552002},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6817485094070435},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.623103678226471},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.6145896315574646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6028290390968323},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.5824028849601746},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5056169033050537},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4310646653175354},{"id":"https://openalex.org/keywords/part-of-speech","display_name":"Part of speech","score":0.3438960313796997},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.27002960443496704},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0668187141418457}],"concepts":[{"id":"https://openalex.org/C161831844","wikidata":"https://www.wikidata.org/wiki/Q2554325","display_name":"Lemmatisation","level":2,"score":0.8845146298408508},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8190890550613403},{"id":"https://openalex.org/C2777842544","wikidata":"https://www.wikidata.org/wiki/Q9056","display_name":"Czech","level":2,"score":0.7601318359375},{"id":"https://openalex.org/C2780684714","wikidata":"https://www.wikidata.org/wiki/Q1271424","display_name":"Part-of-speech tagging","level":3,"score":0.699059009552002},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6817485094070435},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.623103678226471},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.6145896315574646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6028290390968323},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.5824028849601746},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5056169033050537},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4310646653175354},{"id":"https://openalex.org/C123406163","wikidata":"https://www.wikidata.org/wiki/Q82042","display_name":"Part of speech","level":2,"score":0.3438960313796997},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.27002960443496704},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0668187141418457},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/d18-1532","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1532","pdf_url":"https://www.aclweb.org/anthology/D18-1532.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1808.03703","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1808.03703","pdf_url":"https://arxiv.org/pdf/1808.03703","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2886260596","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1808.03703","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1808.03703","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1808.03703","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/d18-1532","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1532","pdf_url":"https://www.aclweb.org/anthology/D18-1532.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6800000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G8645320550","display_name":"Language Research Infrastructure in the Czech Republic","funder_award_id":"LM2015071","funder_id":"https://openalex.org/F4320321005","funder_display_name":"Ministerstvo \u0160kolstv\u00ed, Ml\u00e1de\u017ee a T\u011blov\u00fdchovy"}],"funders":[{"id":"https://openalex.org/F4320321005","display_name":"Ministerstvo \u0160kolstv\u00ed, Ml\u00e1de\u017ee a T\u011blov\u00fdchovy","ror":"https://ror.org/037n8p820"},{"id":"https://openalex.org/F4320321006","display_name":"Grantov\u00e1 Agentura \u010cesk\u00e9 Republiky","ror":"https://ror.org/01pv73b02"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2886260596.pdf","grobid_xml":"https://content.openalex.org/works/W2886260596.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2963714641","https://openalex.org/W2125492538","https://openalex.org/W2991253660","https://openalex.org/W2770603736","https://openalex.org/W144549204","https://openalex.org/W2488290647","https://openalex.org/W102385157","https://openalex.org/W2185970782","https://openalex.org/W2992245086","https://openalex.org/W2161095731","https://openalex.org/W3210039896","https://openalex.org/W3130468549","https://openalex.org/W2122495161","https://openalex.org/W2883188201","https://openalex.org/W3097288631","https://openalex.org/W2142129461","https://openalex.org/W2169160736","https://openalex.org/W2739015351","https://openalex.org/W44431171","https://openalex.org/W2076031003"],"abstract_inverted_index":{"We":[0,26,54],"present":[1],"LemmaTag,":[2],"a":[3],"featureless":[4],"neural":[5],"network":[6],"architecture":[7],"that":[8,28],"jointly":[9],"generates":[10],"part-of-speech":[11,70],"tags":[12],"and":[13,23,43,72,77],"lemmas":[14],"for":[15],"sentences":[16],"by":[17],"using":[18,44],"bidirectional":[19],"RNNs":[20],"with":[21,61],"characterlevel":[22],"word-level":[24],"embeddings.":[25],"demonstrate":[27],"both":[29,69],"tasks":[30],"benefit":[31],"from":[32],"sharing":[33],"the":[34,38,45,52],"encoding":[35],"part":[36],"of":[37],"network,":[39],"predicting":[40],"tag":[41],"subcategories,":[42],"tagger":[46],"output":[47],"as":[48],"an":[49],"input":[50],"to":[51],"lemmatizer.":[53],"evaluate":[55],"our":[56],"model":[57],"across":[58],"several":[59],"languages":[60],"complex":[62],"morphology,":[63],"which":[64],"surpasses":[65],"state-of-the-art":[66],"accuracy":[67],"in":[68,74],"tagging":[71],"lemmatization":[73],"Czech,":[75],"German,":[76],"Arabic.":[78]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}